Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hxy91819/mason-skills --skill distillgit clone --depth 1 https://github.com/hxy91819/mason-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hxy91819/mason-skills/distill)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/distill"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/distill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/distill"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/distill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.05139 |
| Opus 5 | $0.00043 | $0.02570 |
| Sonnet 5 | $0.00017 | $0.01028 |
| Haiku 4.5 | $0.00009 | $0.00514 |
Grade A, and why
distill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill Session Evidence into the Harness and Project Knowledge
Turn session evidence into the smallest verified harness and project-knowledge changes
that make future work more reliable. The harness includes intent and specs, the applicable
AGENTS.md instruction chain, repository Skills and their invocation metadata, tools and
scripts, environment and permissions, and verification and evals. Project knowledge
includes the durable documentation and decision rationale that give humans and agents an
accurate global view of the project.
Follow all four phases. Phase 3 is the single approval gate: confirmation of the proposed candidate set authorizes its smallest in-scope edits. Ask again only for a materially different target, an external repository, or a destructive change. Finish without edits when no candidate survives the evidence and value gates.
Operating Modes
Use one workflow with two evidence scopes:
- Session mode is the default. Review the current conversation and its tool evidence.
- Review mode is explicit or scheduler-invoked. Review a bounded set of recent sessions for recurring patterns, regressions, and the effectiveness of earlier changes.
In review mode, read references/periodic-review.md before Phase 1 and follow its evidence
boundary, batching, privacy, recurrence, and previous-change evaluation rules. A periodic
trigger starts an audit; it never authorizes edits or weakens the Phase 3 approval gate.
The caller or scheduler owns cadence. Distill may use and update a user-local review
checkpoint for the default evidence boundary, but the checkpoint is a soft retrieval
cursor and never prevents the manager from reopening an earlier window when the evidence
calls for it.
BB stage review
When the caller explicitly asks to review a bounded BB stage, use Review mode with the
repo-harness profile. Read BB 阶段复盘 before collecting
threads. It defines the BB-only adapter: how to freeze the boundary, cover interrupted
threads with their continuations, request each session's $distill, and dispatch one
read-only aggregator. The adapter never bypasses this Skill's evidence rules or Phase 3
approval gate.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +24 lines fa2d30dd9ab5
- 11d ago First seen · 403 lines · 86 tokens per session scan A 32cf02578181
distill is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 5,139 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.